System and method for optimizing electronic document layouts

- Overstock.com, Inc.

A system and method is provided that ranks and sorts websites, apps, email, or VR environment content in real-time to increase engagement, CTR, conversions, and revenue. A client applies attributes to sections of the digital content. A server system tracks end user inputs and generates optimized layouts for the digital content, such as a webpage. The document layout is ordered or reorganized before or after the document is delivered to the end user.

Skip to: Description  ·  Claims  ·  References Cited  · Patent History  ·  Patent History
Description
CROSS REFERENCE TO RELATED APPLICATIONS

This document claims the benefit of U.S. Prov. Pat. App. No. 62/335,050 filed on May 11, 2016 and U.S. patent application Ser. No. 15/593,040 filed May 11, 2017, the entireties of which are hereby incorporated by reference.

BACKGROUND OF THE INVENTION

Field of the invention: This invention relates to the general field of network delivered digital content, and more specifically toward a system and method that ranks and sorts mobile, web, and email content in real-time to increase customer engagement, click-through rate (CTR), and/or conversions. A client applies attributes to sections of the digital content. A server system tracks end user inputs and generates optimized layouts for the digital content, such as a webpage. The document layout is ordered or reorganized before or after the document is delivered to the end user.

Just as brick and mortar stores optimize their shelf space and floor-sets to increase conversions and order size, the digital world can also optimize the real estate of their websites, apps, emails, or virtual reality (VR) environment to maximize engagement, CTR, conversions, and revenue. Today, mobile, web, and email optimization are primarily done through data analysis, and AB or multivariate testing. The problem is that these optimizations are manual, non-scalable, and prone to errors.

Manual A/B testing or analytics is how web content optimization has occurred in the past. Analytics, A/B testing, and recommendation platforms can aid developers in optimizing page layout; however, none of these automate the optimization of the user interface. Furthermore, none of these enable real-time layout optimization based upon end-user behavior characteristics.

Thus there has existed a need for a system and method that ranks and sorts mobile, web, and email content in real-time to increase customer engagement, CTR, and/or conversions. Additionally, there is a need for a system that ranks and sorts content in virtual reality platforms, where the layout of a virtual environment can be optimized based on what a user views and interacts with.

SUMMARY OF THE INVENTION

The current disclosure provides just such a solution by having a system that automates the optimization of user interfaces. It restructures the user interface to present the most relevant information. The system can present a unique layout for all users (default), specific segments (cluster) of users, or for a specific user, based on the amount of data available.

Clients integrate their website with this system by adding tracking code to their system. This code tracks the impressions, positions, pixels, clicks, orders, revenue, and even virtual touch or handling of the users of the client's system (website, app, emails, or virtual reality environment). The system then uses randomized testing to rank the positions of content sections and/or subsections, while also ranking and scoring the actual page content. Then, the system places the best content in the best position, and the next best content in the next best position, and so on for the remaining content sections. Machine learning is used to determine the ideal weight of the various metrics used in the score, to maximize the client's key performance indicator (KPI). The KPI may be engagement, conversions, revenue, application signups, email signups, or other performance indicators based on the client's specific needs or specific application of the system.

A time decay function is also used to weigh more recent data more heavily than older data. The current system then uses the content score to sort the content modules (sections) in order, from best performing position to lowest performing position. Within these content sections, the system will also sort subsections of content in the same manner. The sort happens in real-time, and content can be dynamically resized to occupy a smaller or larger modules. The system can also remove content (i.e. sections or subsections) that are not performing well. This could be the result of the content performing below a required threshold (e.g. low conversion or CTR).

In addition, this technology can develop a unique sort for different segments (groups or cohorts) of users. These segments can be passed by the client, or identified by the system itself. In other words, users may experience a unique version of the page, app, email, or VR environment for different geolocations, whether they are new or repeat users, referring URL, or time of day, if it improves the KPI (e.g. CTR, conversion, revenue/impression) being optimized. The segments used can be determined by artificial intelligence (AI) or machine learning (ML) algorithms, and can vary based on the client or the application of the technology.

When data permits, the content sort can also be user specific. In other words, when the system described herein has sufficient data to recommend an optimization to a specific user, it does so. When there is insufficient data, it provides an optimization based upon other criteria or data, such as aggregated data (user segment or default).

Finally, clients of the system select what content modules, or objects, of their page, app, email, or VR environment should be optimized. Furthermore, clients can choose to lock, or pin, content (objects) that they would like to remain static.

It is an object of the invention to provide a system and method for optimizing the placement of content on a webpage, and whether or not to serve that content.

It is another object of the invention to provide a system and method for optimizing webpage content based upon client selected criteria.

It is a further object of this invention to provide a system and method for sorting subsections within a section that is itself sorted on a webpage.

Particular embodiments of the current disclosure have a system for optimizing the layout of an electronic document comprising a database and a processor executing programming logic for interfacing with remote systems, the programming logic configured to provide a content sort service, a track service, and a machine learning process; where the track service accepts end user request data, where the track service stores the end user request data in the database, and where the track service provides the end user request data to the machine learning process; where the machine learning process uses the end user request data to generate and update models, where the models are stored in the database; where the content sort service accepts optimization requests for an electronic document, where the electronic document comprises a plurality of sections, where the content sort service accesses the database to obtain models for the optimization request, where the content sort service selects one or more models from the models obtained from the database; where the content sort service applies the one or more selected models to generate an optimized order for the plurality of sections for the electronic document. The one or more models selected by the content sort service is a randomized model, where the randomized model is used to provide a partial or fully randomized optimized order for the plurality of sections for the electronic document. The content sort service further provides a response to an end user, where the response comprises the optimized order for the plurality of sections for the electronic document. Alternatively, the content sort service further provides a response to a client server, where the response comprises the optimized order for the plurality of sections for the electronic document. Each optimization request for an electronic document comprises data indicating that one or more of the plurality of sections of the electronic document are pinned. The pinned one or more of the plurality of sections of the electronic document are ignored by the content sort service. Each optimization request for an electronic document comprises a key performance indicator, where the content sort service uses the key performance indicator to select the one or more models obtained from the database. The content sort service uses a progressively localized content position randomization to generate an optimized order for the plurality of sections for the electronic document. The track service provides the end user request data to the machine learning process via one or more log files or via a distributed messaging system. At least one of the plurality of sections of the electronic document comprises a plurality of subsections, where the content sort service further applies the one or more selected models to generate an optimized order for the plurality of subsections.

Another embodiment of the current disclosure is a method of optimizing the layout of an electronic document, comprising the steps of: selecting a plurality of sections of the electronic document for optimization; selecting one or more criteria for optimizing the order of the plurality of sections of the electronic document; sending a request to a server system to optimize the plurality of sections of the electronic document using the one or more criteria; and upon receiving an optimization response from the server system, rearranging the sections of the electronic document according to the optimization response received from the server system. The method further comprises the step of resizing the sections of the electronic document. The method further comprises the step of removing one or more sections from the electronic document if it fails to meet predefined minimum criteria. At least one of the plurality of sections of the electronic document comprises a plurality of subsections, where the method further comprises the step of sending a request to a server system to optimize the plurality of subsections of the electronic document using the one or more criteria; and upon receiving a subsection optimization response from the server system, rearranging the subsections according to the subsection optimization response received from the server system. The method further comprises the step of adding one or more attributes to one or more of the plurality of sections of the electronic document.

Further embodiments of the current disclosure have a system for optimizing the layout of an electronic document comprising a processor executing programming logic for interfacing with remote systems, the programming logic configured to: accept a request for an electronic document from an end user system, send an optimization request to a server system for an optimized layout of the electronic document, where the electronic document comprises a plurality of sections; receive an optimized layout response from the server system, rearrange the sections of the electronic document according to the optimized layout response from the server system; and send an electronic document response to the end user system, where the sections of the electronic document are rearranged. The optimization request comprises a key performance indicator. At least one of the sections of the electronic document comprises a plurality of subsections, where the programming logic is further configured to rearrange the subsections according to the optimized layout response from the server system. The electronic document response sent to the end user system comprises computer readable instructions, where the computer readable instructions comprise instructions to send input data generated by the end user to the server system.

As used herein, a client is an entity that provides webpage, app, email, VR, or other electronic document content to end users and sets the criteria on the server system that generates the optimized webpage, app, email, VR, or other electronic document content order or layout. An end user, or simply user, is the entity that is requesting and viewing the electronic document content of a client. The webpage layout is optimized for the end user. The electronic document, which includes without limitation webpage, app, email, and VR content, has two or more sections and/or subsections that can be reorganized or optimized.

While particular programming languages, file structures, databases, and operating systems may be discussed herein, other languages, file structures, databases, and operating systems may be implemented without departing from the scope of the current disclosure.

Terms and phrases used in this document, and variations thereof, unless otherwise expressly stated, should be construed as open ended as opposed to limiting. As examples of the foregoing: the term “including” should be read as meaning “including, without limitation” or the like; the term “example” is used to provide exemplary instances of the item in discussion, not an exhaustive or limiting list thereof; the terms “a” or “an” should be read as meaning “at least one,” “one or more” or the like; and adjectives such as “conventional,” “traditional,” “normal,” “standard,” “known” and terms of similar meaning should not be construed as limiting the item described to a given time period or to an item available as of a given time, but instead should be read to encompass conventional, traditional, normal, or standard technologies that may be available or known now or at any time in the future. Likewise, where this document refers to technologies that would be apparent or known to one of ordinary skill in the art, such technologies encompass those apparent or known to the skilled artisan now or at any time in the future.

The presence of broadening words and phrases such as “one or more,” “at least,” “but not limited to” or other like phrases in some instances shall not be read to mean that the narrower case is intended or required in instances where such broadening phrases may be absent. Additionally, the various embodiments set forth herein are described in terms of exemplary block diagrams, flowcharts and other illustrations. As will become apparent to one of ordinary skill in the art after reading this document, the illustrated embodiments and their various alternatives can be implemented without confinement to the illustrated examples. For example, block diagrams and their accompanying description should not be construed as mandating a particular architecture or configuration.

There has thus been outlined, rather broadly, the more important features of the invention in order that the detailed description thereof may be better understood, and in order that the present contribution to the art may be better appreciated. There are additional features of the invention that will be described hereinafter and which will form the subject matter of the claims appended hereto. The features listed herein and other features, aspects and advantages of the present invention will become better understood with reference to the following description and appended claims.

BRIEF DESCRIPTION OF THE FIGURES

The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments of the invention and together with the description, serve to explain the principles of this invention.

FIG. 1 is diagram showing an original page layout according to selected embodiments of the current disclosure.

FIG. 2 is a diagram showing an optimized page layout according to selected embodiments of the current disclosure.

FIG. 3 is a flowchart showing the interaction between the client webpage and the server system according to selected embodiments of the current disclosure.

FIG. 4 is a flowchart showing a process for providing an optimized webpage layout using a client-side integration according to selected embodiments of the current disclosure.

FIG. 5 is a flowchart showing an alternative process for providing an optimized webpage layout according to selected embodiments of the current disclosure.

FIG. 6 is a flowchart showing another alternative process for providing an optimized webpage layout according to selected embodiments of the current disclosure.

FIG. 7 is a flowchart showing a process executed on a server system for handling optimization requests from remote clients.

FIG. 8 is diagram showing the interactions between the client website and the server system according to selected embodiments of the current disclosure.

FIG. 9 is a flowchart showing a process for providing an optimized webpage layout using server-side processes according to selected embodiments of the current disclosure.

 DETAILED DESCRIPTION OF THE INVENTION

Many aspects of the invention can be better understood with the references made to the drawings below. The components in the drawings are not necessarily drawn to scale. Instead, emphasis is placed upon clearly illustrating the components of the present invention. Moreover, like reference numerals designate corresponding parts through the several views in the drawings.

FIG. 1 is diagram showing an original page layout according to selected embodiments of the current disclosure. The page includes a header and a footer, with four sections there between labeled A, B, C, and D. Each section may have 1 or more subsections therein. For example, section A has subsections 1, 2, 3, 4, and 5; section B has just one subsection, section C has subsections 1, 2, 3, 4, and 5, and section D has subsections 1, 2, and 3. Each section may have a different layout, such that the subsections are arranged differently compared to other sections.

FIG. 2 is a diagram showing an optimized page layout according to selected embodiments of the current disclosure. As with the original page layout, the optimized page layout includes a header at the top and a footer at the bottom. However, the placement of the sections has been modified to optimize the layout. While section A remains at the top of the page, it is now followed by section C. Section D follows section C, with the last Section B placed at the bottom.

Furthermore, the subsections within each section have been optimized as well. For example, section A previously had a larger subsection 1, with subsections 2 through 5 beneath it. Now, however, section A has a larger subsection 4, with subsections 1, 2, 5, and 3 beneath it. In fact, each section, subsection, or both may be resized to fit within the available content area. As shown in FIGS. 1, and 2, subsections 1 and 2 are resized to fit the allocated space.

FIG. 3 is a flowchart showing the interaction between the client webpage and the server system according to selected embodiments of the current disclosure. The client webpage 10 sends an optimization request 11 to a server system 12. The server system 12 processes that request, and returns an optimization response 13 to the client webpage to act upon. The client webpage uses the optimization response to optimize the webpage layout.

FIG. 4 is a flowchart showing a process for providing an optimized webpage layout using a client-side integration according to selected embodiments of the current disclosure. Attributes are added 41 by the client to the client's webpage on the client's server 71. These attributes apply to particular sections or subsections of a webpage that the client wants optimized by the server system 12. Additionally, the client adds JavaScript code 42, or alternatively, a reference to download a JavaScript file that includes the JavaScript code. The JavaScript code includes computer readable instructions for interacting with the server system (such as tracking user behavior) and optimizing the content of the webpage. An end user 72 (or the end user's system or browser) then loads the client's webpage 43.

After loading the page, including the instructions contained in the JavaScript code or file, the instructions are executed and a request is made 44 to the server system 12 to obtain an optimized layout or order for the webpage downloaded by the end user 72. The server system 12 generates such an optimized order or layout, and returns a response with the optimized order 45 back to the end user 72. The instructions contained in the JavaScript code then optimize the webpage order or layout based upon the data received from the server system 12. The sections and subsections of the webpage are reorganized and moved around to optimize the content based upon the attributes set by the client. End user inputs, including without limitation impressions, clicks, and orders, are sent 46 to the server system 12. This input data is used to generate future optimized content for that particular end user, as well as other end users.

FIG. 5 is a flowchart showing a process for providing an optimized webpage layout according to selected embodiments of the current disclosure. An end user makes a request to view a particular webpage, and that webpage request 20 is processed by a client server. The client server sends an optimization request 21 to the server system, which processes and generates optimization responses, discussed in more detail below. If the client server does not receive a response 22, or the response 22 is invalid, the client server sends default content 23 to the end user. If, on the other hand, the client server receives a valid response 22, it generates an optimized layout 24 using the response from the server system. For example, the client server will use the data in the response to organize a webpage from its original format, such as the one shown in FIG. 1, to produce the layout in an optimized format, such as the one shown in FIG. 2. The optimized content is then sent 25 to the end user.

FIG. 6 is a flowchart showing an alternative process for providing an optimized webpage layout according to selected embodiments of the current disclosure. As in FIG. 5, an end user makes a request to view a particular webpage, and that webpage request 20 is processed by a client server. However, in this figure, the client server sends the page content 26 to the end user, which includes a reference to one or more scripts used to access and interact with the server system. The end user, or more specifically, the browser of the end user, loads the optimizer scripts 27 and then sends an optimization request 21 to the server system. If no response 22 is received from the server system, or an invalid response 22 is received from the server system, the page content originally received by the end user is left unchanged 28. If, on the other hand, a valid response 22 is received from the server system, the content received from the client server is reorganized 29 by the optimizer scripts to produce an optimized layout for the end user.

FIG. 7 is a flowchart showing a process executed on a server system for handling optimization requests from remote clients. The server system receives an optimization request 30, and then determines whether the request is authentic 31. In other words, it determines if the request is made from a webpage with a valid account that has been configured properly. If the server system determines that the request is not authentic or not valid 31, then the server system sends an error response 32. If, on the other hand, the server system determines that the request is authentic and valid 31, then the server system proceeds in generating an optimized sort order for an optimized layout 34. It then sends the optimized sort order response 35 back to the requestor.

FIG. 8 is diagram showing the interactions between the client website and the server system according to selected embodiments of the current disclosure. The client website 10 interacts with the server system 12, whether through the client server or the end user's machine, through at least two services: a content sort service 15, and a track service 16. The content sort service 52 is a runtime component that returns the optimized sort order of the sections and/or subsections of a requested webpage. The track service 16 is a web service that tracks specific events, such as impressions and clicks. It writes events to a log file 17 as well as to the database 14. The log files may be written to in JSON format, and the data stored in a NoSQL database. The database 14 stores tracking information and is used by the content sort service 15 to provide optimized orders of sections and/or subsections of webpages. A machine learning (ML) process 18 generates aggregate data based on the tracked events as well as generates models based on online learning algorithms, discussed in more detail below. The generated models are stored into the database 14.

The content sort process begins when a client webpage 10 sends a request to the content sort service 15 of the server system 12 for an optimized layout. The content sort service 15 accesses the database 14 to determine whether the webpage is configured correctly, including without limitation whether the client webpage is authorized to access this service and if so, what KPI have been set for this particular webpage or, alternatively, whether there is sufficient data to automatically determine which KPI(s) to use based upon the different weights assigned to each KPI by the client. Subsequently, the content sort service 15 accesses the database 14 to find all applicable models for this particular request given the KPI(s) that are to be used. Models describe the predicted performance of content at different sort positions, as well as the relative strength of different positions within the webpage. The content sort service 15 generates scores for each of these models and uses the scores to determine which models to use. For example, each applicable model is given a score relative to its perceived ability to generate the optimal layout for a particular webpage for the particular user given the KPI(s) that are set for that particular webpage. The model with the best score is used to determine the sort order for the sections and/or subsections of this webpage.

Embodiments of the current disclosure also provide for the content sort process to designate sections or subsections for removal. If a particular model determines that a certain section or subsection does not meet or exceed a predefined minimum score or criteria, that section or subsection is removed from the layout. The removed content may be replaced with other content, or is simply not displayed in the electronic document.

For each request to the content sort service 15, the request will be randomly assigned to return either a “learning” response or an “optimized” response. For requests that are assigned to return an optimized response, the optimized sort order data representing the optimized order of the sections and/or subsections is returned to the webpage. For requests that are assigned to return a learning response, the optimized sort order data is at least partially randomized to allow the machine learning process to more efficiently test and predict an optimal content sort order. The randomization process for learning requests uses a progressively localized content position randomization whereby new content is randomly ordered across a wide range of positions, and as impression volumes increase, the content is randomly ordered across a progressively narrower range of positions around the calculated optimal position. This is designed in a way so as to minimize the learning costs for the machine learning algorithm. The resulting randomized sort order data representing the order of sections and/or subsections is returned to the webpage.

The track service 16 takes end user request or input data, such as impressions and clicks, and saves it to the database 14 as well as to log file(s) 17.

The machine learning process 18 is run continuously, at set increments of time, or at variable increments of time. The machine learning process 18 looks at log files 17 to process new events (end user request data) as they come in or shortly thereafter. Instead of reading log files, the machine learning process 18 can access the end user request data events using a distributed messaging system/service 19, such as Apache Kafka. In either instances, the machine learning process 18 aggregates data based on event type, such as impressions, clicks, conversion, revenue, and a/b test. Models are generated and regenerated using online learning algorithms, discussed in more detail below. The machine learning process 18 may also evaluate multiple algorithms to determine which model is most likely to provide the best optimized layout. Furthermore, multiple models may be combined together using Ensemble Learning methodologies, such as bucket of models, to provide more accurate models. The models generated by the machine learning process 18 are saved to the database 14 for use by the content sort service 15.

Machine learning algorithms, such as sequential learning, are used to create models for predicting and generating an optimized order of sections and/or subsections of the webpage. The content sort service uses these models to generate the optimized order data in response to requests for an optimized webpage layout.

In sequential learning, the algorithm attempts to minimize the error between a predicted optimized layout and an actual optimized layout. The machine learning process receives input data, such as from the log file or distributed messaging system. It uses this input to make a prediction of the optimized layout, or in other words, creates a model that generates an optimized layout. The optimized layout is displayed to an end user. The end user interacts with the layout, and generates additional end user request data, which is then received by the machine learning process. The machine learning process evaluates the error in its optimized layout, and updates its model to provide an improved model to generate optimized layouts.

By way of example, the machine learning process receives input data from a webpage with three sections: A, B, and C. It generates a model and saves that model to the database. An end user visits the webpage, and the webpage requests an optimized layout. The content sort service is looking to optimize click through by the user, that is, the webpage should be optimized such that the user clicks on at least one of the sections to travel to another page. Using the model generated by the machine learning process, the content sort service determines that the optimal layout is section B followed by section C, which is then followed by section A. This order data is delivered to the webpage, which is reordered and displayed to the end user. An optimal page layout would have the user clicking on the first section, that is, section B. However, the end user does not click on section B or section C, but rather clicks on the last section A. Another end user that is displayed this same layout does not click on any of the sections. These events are sent to the track service, which distributes the data to the machine learning process through log files or a distributed messaging system/service. The machine learning process evaluates the event data and determines that the optimized layout that should have been sent to the end users was section A followed by section B, which should have been followed by section C. The machine learning process updates its model accordingly, and saves it to the database.

The client selects which layouts it would like optimized, and the criteria or KPI used to optimize those layouts. Instead of selecting a specific KPI, the client may set an order of KPI to be used, or even apply a preference or weight to each KPI. The content sort service will then use the preferences or weights of each KPI to determine which model to use to provide the optimized order to generate the optimized layout of the web page.

In addition to selecting which sections should be optimized, users may also “pin” or select certain sections that should remain static or stationary relative to other sections. This can be helpful when a client wishes a particular section to be first, last, or follow or precede another section.

When a section is pinned, this section can be completely ignored. The optimization request leaves out the section in its request to the content sort service, and the content sort service returns an optimized sort order for the sections without regard to the pinned section. For example, a header section that is always displayed first, or a footer section that is always displayed last, is considered “pinned” and can be ignored by the system. Alternatively, the pinned section may be included in the request to the content sort service, but with a flag or an attribute that signifies the particular section has been pinned, and how it has been pinned (for example, first, last, or relative to another section). This may be relevant data to the content sort service to determine the model and/or may be used as input to the model to determine the optimized sort order. For example, when a particular section is pinned first, that may modify the optimal order generated by the models for a particular end user.

FIG. 9 is a flowchart showing a process for providing an optimized webpage layout using server-side processes according to selected embodiments of the current disclosure. The client adds attributes 41 to the sections and subsections of the electronic document (e.g., website) residing on the client's server 71 that the client wants optimized. The client also adds a JavaScript code or file 42 to their website or electronic document distribution system. This file is used to track user behavior (e.g. clicks, impressions, conversions, etc.). Additionally, the client installs a server-side script or code 49 on the client's server(s) that is responsible for the optimization of the electronic document. The client's website and server are then ready to accept requests. A user requests the client's page. The client's server makes a request to the content sort service of the server system to get the optimized order for the electronic document 44. The content sort service of the server system generates (as discussed above) and then returns the requested optimized order data 45, and the client's server 71 (through the instructions provided for in the server-side script or code on the client's server(s)) compares the optimized order with the current electronic document and moves the necessary elements. The client server 71 renders the optimized electronic document with the newly ordered elements and provides the electronic document to the end user 48. Inputs generated by the user while interacting with the electronic document (e.g., impressions, clicks, orders, etc.) are sent 46 to the track service of the server system 12 (per the instructions provided for in the JavaScript file) such that the server system may calculate optimized sorts and ordering for subsequent requested electronic documents.

While various embodiments of the present invention have been described above, it should be understood that they have been presented by way of example only, and not of limitation. Likewise, the various diagrams may depict an example architectural or other configuration for the invention, which is provided to aid in understanding the features and functionality that can be included in the invention. The invention is not restricted to the illustrated example architectures or configurations, but the desired features can be implemented using a variety of alternative architectures and configurations.

Indeed, it will be apparent to one of skill in the art how alternative functional configurations can be implemented to implement the desired features of the present invention. Additionally, with regard to flow diagrams, operational descriptions and method claims, the order in which the steps are presented herein shall not mandate that various embodiments be implemented to perform the recited functionality in the same order unless the context dictates otherwise.

Although the invention is described above in terms of various exemplary embodiments and implementations, it should be understood that the various features, aspects and functionality described in one or more of the individual embodiments are not limited in their applicability to the particular embodiment with which they are described, but instead can be applied, alone or in various combinations, to one or more of the other embodiments of the invention, whether or not such embodiments are described and whether or not such features are presented as being a part of a described embodiment. Thus, the breadth and scope of the present invention should not be limited by any of the above-described exemplary embodiments.

Claims

1. A system for determining the optimal layout of digital content comprising a database and a processor executing programming logic for interfacing with remote systems, the programming logic configured to provide:

a content sort service;
an optimized response generator;
a learning response generator;
wherein the content sort service accepts an optimization request for the digital content where the digital content comprises a plurality of sections;
wherein the content sort service randomly assigns the optimization request to the optimized response generator or the learning response generator;
wherein the optimized response generator produces an optimized response using an optimized order for the digital content, wherein the content sort service stores the optimized order in the database;
wherein the learning response generator randomizes at least a portion of the optimized order stored in the content sort service to produce a learning response;
wherein the learning response or the optimized response are provided to an end user;
wherein a machine learning process tracks the use of the learning responses produced by the learning response generator and uses the data to improve the optimized order for the plurality of sections, and;
wherein the machine learning process uses a progressively narrowed range of content position randomization to improve the optimized order for the plurality of sections.

2. The system of claim 1 wherein the content sort service further provides a response to an end user, where the response comprises the optimized order for the plurality of sections of the digital content.

3. The system of claim 1, wherein the content sort service further provides a response to a client server, where the response comprises the optimized order for the plurality of sections for the digital content.

4. The system of claim 1, wherein the optimization request for digital content comprises data indicating that one or more of the plurality of sections of the digital content are pinned.

5. The system of claim 4, wherein the pinned sections of the digital content are ignored by the content sort service.

6. The system of claim 1, wherein the optimization request for digital content additionally comprises a key performance indicator, and wherein the machine learning process uses the key performance indicator to determine how to optimize the digital content.

7. The system of claim 1, further comprising a track service, where the track service stores end user request data in a database.

8. The system of claim 1, wherein at least one of the plurality of sections of the digital content comprises a plurality of subsections, where the content sort service further generates an optimized order for the plurality of subsections.

9. A method of optimizing the layout of digital content comprising the steps of:

accepting an optimization request for the digital content, wherein the digital content comprises a plurality of sections;
randomly assigning the optimization request to an optimized response generator or a learning response generator;
wherein the optimized response generator presents an optimized order for the plurality of sections, wherein an optimized order for the plurality of sections is stored in memory;
wherein the learning response generator takes the optimized order for the plurality of sections and randomly rearranges at least part of the optimized order to generate a learning response;
providing the learning response or the optimized response to an end user; and
tracking the use of the learning responses produced by the learning response generator and using a machine-learning system with the data to improve the optimized order for the plurality of sections;
wherein the machine learning system uses a progressively narrowed range of content position randomization to generate an optimized order for the plurality of sections of the digital content.

10. The method of claim 9, further comprising the step of resizing the sections of the digital content based on the optimized order for the plurality of sections.

11. The method of claim 9, further comprising the step of removing one or more sections of the digital content.

12. The method of claim 9, wherein at least one of the plurality of sections of the digital content comprises a plurality of subsections, where the method further comprises the step of generating an optimized order for the plurality of subsections.

13. The method of claim 9, further comprising the step of adding one or more attributes to one or more of the plurality of sections of the digital content.

14. The method of claim 9, wherein the optimization request comprises a key performance indicator.

15. A system for optimizing the layout of digital content comprising a database and a processor executing programming logic for interfacing with remote systems, the programming logic configured to provide: a content sort service and a machine learning process;

where the content sort service accepts an optimization request for the electronic document, where the digital content comprises a plurality of sections;
wherein the content sort service produces an optimized response using an optimized order for the plurality of sections of the digital content stored in the database;
wherein the content sort service randomizes at least a portion of the optimized response to produce a learning response; wherein the content sort service randomly determines whether to return an optimized response or a learning response in response to the optimization request;
where the machine learning process uses end user request data from a progressively narrowed range of content position randomization to generate an optimized order for the plurality of sections for the digital content.

16. The system of claim 15, wherein the content sort service further provides a response to an end user, where the response comprises the optimized order for the plurality of sections for the digital content.

17. The system of claim 15, wherein the content sort service further provides a response to a client server, where the response comprises the optimized order for the plurality of sections for the digital content.

18. The system of claim 15, wherein the optimization request for digital content comprises a key performance indicator, where the content sort service additionally uses the key performance indicator to determine how to optimize the order for the plurality of sections for the digital content.

Referenced Cited
U.S. Patent Documents
3573747 April 1971 Adams et al.
3581072 May 1971 Nymeyer
4412287 October 25, 1983 Braddock, III
4674044 June 16, 1987 Kalmus et al.
4677552 June 30, 1987 Sibley, Jr.
4789928 December 6, 1988 Fujisaki
4799156 January 17, 1989 Shavit et al.
4808987 February 28, 1989 Takeda et al.
4823265 April 18, 1989 Nelson
4854516 August 8, 1989 Yamada
4903201 February 20, 1990 Wagner
RE33316 August 28, 1990 Katsuta et al.
5027110 June 25, 1991 Chang et al.
5053956 October 1, 1991 Donald et al.
5063507 November 5, 1991 Lindsey et al.
5077665 December 31, 1991 Silverman et al.
5101353 March 31, 1992 Lupien et al.
5136501 August 4, 1992 Silverman et al.
5168446 December 1, 1992 Wiseman
5205200 April 27, 1993 Wright
5243515 September 7, 1993 Lee
5258908 November 2, 1993 Hartheimer et al.
5280422 January 18, 1994 Moe et al.
5297031 March 22, 1994 Gutterman et al.
5297032 March 22, 1994 Trojan et al.
5301350 April 5, 1994 Rogan et al.
5305200 April 19, 1994 Hartheimer et al.
5325297 June 28, 1994 Bird et al.
5329589 July 12, 1994 Fraser et al.
5347632 September 13, 1994 Filepp et al.
5375055 December 20, 1994 Togher et al.
5377354 December 27, 1994 Scannell et al.
5394324 February 28, 1995 Clearwater
5407433 April 18, 1995 Loomas
5411483 May 2, 1995 Loomas et al.
5426281 June 20, 1995 Abecassis
5485510 January 16, 1996 Colbert
5493677 February 20, 1996 Balogh et al.
5553145 September 3, 1996 Micali
5557728 September 17, 1996 Garrett et al.
5579471 November 26, 1996 Barber et al.
5596994 January 28, 1997 Bro
5598557 January 28, 1997 Doner et al.
5621790 April 15, 1997 Grossman et al.
5640569 June 17, 1997 Miller et al.
5657389 August 12, 1997 Houvener
5664111 September 2, 1997 Nahan et al.
5664115 September 2, 1997 Fraser
5689652 November 18, 1997 Lupien et al.
5694546 December 2, 1997 Reisman
5706457 January 6, 1998 Dwyer et al.
5710889 January 20, 1998 Clark et al.
5715314 February 3, 1998 Payne et al.
5715402 February 3, 1998 Popolo
5717989 February 1998 Tozzoli et al.
5721908 February 24, 1998 Lagarde et al.
5722418 March 3, 1998 Bro
5727165 March 10, 1998 Ordish et al.
5737599 April 7, 1998 Rowe et al.
5760917 June 2, 1998 Sheridan
5761496 June 2, 1998 Hattori
5761655 June 2, 1998 Hoffman
5761662 June 2, 1998 Dasan
5771291 June 23, 1998 Newton et al.
5771380 June 23, 1998 Tanaka et al.
5778367 July 7, 1998 Wesinger, Jr. et al.
5790790 August 4, 1998 Smith et al.
5794216 August 11, 1998 Brown
5794219 August 11, 1998 Brown
5796395 August 18, 1998 de Hond
5799285 August 25, 1998 Klingman
5803500 September 8, 1998 Mossberg
5818914 October 6, 1998 Fujisaki
5826244 October 20, 1998 Huberman
5835896 November 10, 1998 Fisher et al.
5845265 December 1, 1998 Woolston
5845266 December 1, 1998 Lupien et al.
5850442 December 15, 1998 Muftic
5870754 February 9, 1999 Dimitrova et al.
5872848 February 16, 1999 Romney et al.
5873069 February 16, 1999 Reuhl et al.
5873080 February 16, 1999 Coden et al.
5884056 March 16, 1999 Steele
5890138 March 30, 1999 Godin et al.
5890175 March 30, 1999 Wong et al.
5905975 May 18, 1999 Ausubel
5907547 May 25, 1999 Foldare et al.
5913215 June 15, 1999 Rubinstein et al.
5922074 July 13, 1999 Richard et al.
5924072 July 13, 1999 Havens
5926794 July 20, 1999 Fethe
5948040 September 7, 1999 DeLorme et al.
5948061 September 7, 1999 Merriman et al.
5970490 October 19, 1999 Morgenstern
5974396 October 26, 1999 Anderson et al.
5974412 October 26, 1999 Hazlehurst et al.
5986662 November 16, 1999 Argiro et al.
5987446 November 16, 1999 Corey et al.
5991739 November 23, 1999 Cupps et al.
5999915 December 7, 1999 Nahan et al.
6012053 January 4, 2000 Pant et al.
6029141 February 22, 2000 Bezos et al.
6035288 March 7, 2000 Solomon
6035402 March 7, 2000 Vaeth et al.
6044363 March 28, 2000 Mori et al.
6045447 April 4, 2000 Yoshizawa et al.
6047264 April 4, 2000 Fisher et al.
6049797 April 11, 2000 Guha et al.
6055518 April 25, 2000 Franklin et al.
6058379 May 2, 2000 Odom et al.
6058417 May 2, 2000 Hess et al.
6058428 May 2, 2000 Wang et al.
6061448 May 9, 2000 Smith et al.
6065041 May 16, 2000 Lum et al.
6070125 May 30, 2000 Murphy et al.
6073117 June 6, 2000 Oyanagi et al.
6078914 June 20, 2000 Redfern
6085176 July 4, 2000 Woolston
6104815 August 15, 2000 Alcorn et al.
6119137 September 12, 2000 Smith et al.
6128649 October 3, 2000 Smith et al.
6141010 October 31, 2000 Hoyle
6167382 December 26, 2000 Sparks et al.
6178408 January 23, 2001 Coppie et al.
6185558 February 6, 2001 Bowman et al.
6192407 February 20, 2001 Smith et al.
6199077 March 6, 2001 Inala et al.
6202051 March 13, 2001 Woolston
6202061 March 13, 2001 Khosla et al.
6226412 May 1, 2001 Schwab
6243691 June 5, 2001 Fisher et al.
6269238 July 31, 2001 Iggulden
6271840 August 7, 2001 Finseth et al.
6275820 August 14, 2001 Navin-Chandra et al.
6275829 August 14, 2001 Angiulo et al.
6356879 March 12, 2002 Aggarwal et al.
6356905 March 12, 2002 Gershman et al.
6356908 March 12, 2002 Brown et al.
6366899 April 2, 2002 Kemz
6370527 April 9, 2002 Singhal
6373933 April 16, 2002 Sarkki et al.
6374260 April 16, 2002 Hoffert et al.
6381510 April 30, 2002 Amidhozour et al.
6415270 July 2, 2002 Rackson et al.
6415320 July 2, 2002 Hess et al.
6434556 August 13, 2002 Levin et al.
6456307 September 24, 2002 Bates et al.
6460020 October 1, 2002 Pool et al.
6466917 October 15, 2002 Goyal et al.
6484149 November 19, 2002 Jammes et al.
6489968 December 3, 2002 Ortega et al.
6522955 February 18, 2003 Colborn
6523037 February 18, 2003 Monahan et al.
6601061 July 29, 2003 Holt et al.
6604107 August 5, 2003 Wang
6625764 September 23, 2003 Dawson
6643696 November 4, 2003 Davis et al.
6661431 December 9, 2003 Stuart et al.
6665838 December 16, 2003 Brown et al.
6675178 January 6, 2004 Chinchar et al.
6694436 February 17, 2004 Audebert
6701310 March 2, 2004 Sugiura et al.
6718536 April 6, 2004 Dupaquis
6725268 April 20, 2004 Jacket et al.
6728704 April 27, 2004 Mao et al.
6732161 May 4, 2004 Hess et al.
6732162 May 4, 2004 Wood et al.
6801909 October 5, 2004 Delgado et al.
6856963 February 15, 2005 Hurwitz
6889054 May 3, 2005 Himmel et al.
6907401 June 14, 2005 Vittal et al.
6912505 June 28, 2005 Linden et al.
6925307 August 2, 2005 Mamdani et al.
6978273 December 20, 2005 Bonneau et al.
7043450 May 9, 2006 Velez et al.
7069242 June 27, 2006 Sheth et al.
7076453 July 11, 2006 Jammes et al.
7076504 July 11, 2006 Handel et al.
7080030 July 18, 2006 Eglen et al.
7099891 August 29, 2006 Harris et al.
7100111 August 29, 2006 McElfresh et al.
7100195 August 29, 2006 Underwood
7117207 October 3, 2006 Kerschberg et al.
7127416 October 24, 2006 Tenorio
7165091 January 16, 2007 Lunenfeld
7167910 January 23, 2007 Farnham et al.
7216115 May 8, 2007 Walters et al.
7240016 July 3, 2007 Sturgis et al.
7254547 August 7, 2007 Beck et al.
7305614 December 4, 2007 Chen et al.
7318037 January 8, 2008 Solari
7324966 January 29, 2008 Scheer
7340249 March 4, 2008 Moran et al.
7349668 March 25, 2008 Ilan et al.
7353188 April 1, 2008 Yim et al.
7366755 April 29, 2008 Cuomo et al.
7379890 May 27, 2008 Myr et al.
7380217 May 27, 2008 Gvelesiani
7383320 June 3, 2008 Silberstein et al.
7401025 July 15, 2008 Lokitz
7447646 November 4, 2008 Agarwal et al.
7451476 November 11, 2008 Banks et al.
7454464 November 18, 2008 Puthenkulam et al.
7457730 November 25, 2008 Degnan
7493521 February 17, 2009 Li et al.
7496525 February 24, 2009 Mitchell
7496527 February 24, 2009 Silverstein et al.
7496582 February 24, 2009 Farnham et al.
7516094 April 7, 2009 Perkowski
7539696 May 26, 2009 Greener et al.
7546625 June 9, 2009 Kamangar
7552067 June 23, 2009 Nephew et al.
7565615 July 21, 2009 Ebert
7606743 October 20, 2009 Orzell et al.
7610212 October 27, 2009 Klett et al.
7653573 January 26, 2010 Hayes, Jr. et al.
7834883 November 16, 2010 Adams
7904348 March 8, 2011 Johnson et al.
7912748 March 22, 2011 Rosenberg et al.
7921031 April 5, 2011 Crysel et al.
7941751 May 10, 2011 Ebert
7979340 July 12, 2011 MacDonald Korth et al.
7983950 July 19, 2011 De Vita
7983963 July 19, 2011 Byrne et al.
8086643 December 27, 2011 Tenorio
8112303 February 7, 2012 Eglen et al.
8140989 March 20, 2012 Cohen et al.
8166155 April 24, 2012 Rachmeler
8204799 June 19, 2012 Murray et al.
8214264 July 3, 2012 Kasavin et al.
8214804 July 3, 2012 Robertson
8260852 September 4, 2012 Cselle
8312056 November 13, 2012 Peng et al.
8326662 December 4, 2012 Byrne et al.
8370269 February 5, 2013 MacDonald-Korth et al.
8370435 February 5, 2013 Bonefas et al.
8392356 March 5, 2013 Stoner et al.
8452691 May 28, 2013 MacDonald Korth et al.
8473316 June 25, 2013 Panzitta et al.
8494912 July 23, 2013 Fraser et al.
8545265 October 1, 2013 Sakamoto et al.
8577740 November 5, 2013 Murray et al.
8583480 November 12, 2013 Byrne
8630960 January 14, 2014 Gross
8676632 March 18, 2014 Watson et al.
8693494 April 8, 2014 Fiatal
8719075 May 6, 2014 MacDonald Korth et al.
8793650 July 29, 2014 Hilerio et al.
9047341 June 2, 2015 Pan
9047642 June 2, 2015 Byrne et al.
9448692 September 20, 2016 Mierau et al.
9483788 November 1, 2016 Martin
9741080 August 22, 2017 Byrne
9747622 August 29, 2017 Johnson et al.
9805425 October 31, 2017 MacDonald-Korth et al.
9928752 March 27, 2018 Byrne et al.
9940659 April 10, 2018 Behbahani et al.
10013500 July 3, 2018 McClintock
10074118 September 11, 2018 Johnson et al.
10102287 October 16, 2018 Martin
10269081 April 23, 2019 Byrne
10423997 September 24, 2019 MacDonald-Korth et al.
10534845 January 14, 2020 Noursalehi
10769219 September 8, 2020 Martin
10810654 October 20, 2020 Robertson et al.
10853891 December 1, 2020 MacDonald-Korth et al.
10872350 December 22, 2020 Hu et al.
10896451 January 19, 2021 Johnson et al.
10929890 February 23, 2021 Knab et al.
10949876 March 16, 2021 Johnson et al.
10970463 April 6, 2021 Noursalehi
10970769 April 6, 2021 Iqbal
20010014868 August 16, 2001 Herz et al.
20010034667 October 25, 2001 Petersen
20010034668 October 25, 2001 Whitworth
20010044751 November 22, 2001 Pugliese, III et al.
20010047290 November 29, 2001 Petras et al.
20010047308 November 29, 2001 Kaminsky et al.
20010051996 December 13, 2001 Cooper et al.
20020002513 January 3, 2002 Chiasson
20020007321 January 17, 2002 Burton
20020007356 January 17, 2002 Rice et al.
20020013721 January 31, 2002 Dabbiere et al.
20020019763 February 14, 2002 Linden et al.
20020022995 February 21, 2002 Miller et al.
20020023059 February 21, 2002 Bari et al.
20020026390 February 28, 2002 Ulenas et al.
20020029187 March 7, 2002 Meehan et al.
20020038312 March 28, 2002 Donner et al.
20020040352 April 4, 2002 McCormick
20020042738 April 11, 2002 Srinivasan et al.
20020049622 April 25, 2002 Lettich et al.
20020056044 May 9, 2002 Andersson
20020065774 May 30, 2002 Young et al.
20020099578 July 25, 2002 Eicher, Jr. et al.
20020099579 July 25, 2002 Stowell et al.
20020099602 July 25, 2002 Moskowitz et al.
20020107718 August 8, 2002 Morrill et al.
20020107853 August 8, 2002 Hofmann et al.
20020111826 August 15, 2002 Potter et al.
20020120537 August 29, 2002 Morea et al.
20020120609 August 29, 2002 Lang et al.
20020123957 September 5, 2002 Notarius et al.
20020124100 September 5, 2002 Adams
20020129282 September 12, 2002 Hopkins
20020133502 September 19, 2002 Rosenthal et al.
20020138399 September 26, 2002 Hayes et al.
20020147625 October 10, 2002 Koike, Jr.
20020156802 October 24, 2002 Takayama et al.
20020161648 October 31, 2002 Mason et al.
20020161664 October 31, 2002 Shaya et al.
20020188777 December 12, 2002 Kraft et al.
20020194049 December 19, 2002 Boyd
20020198784 December 26, 2002 Shaak et al.
20020198882 December 26, 2002 Linden et al.
20030004855 January 2, 2003 Dutta et al.
20030005046 January 2, 2003 Kavanagh et al.
20030009362 January 9, 2003 Cifani et al.
20030009392 January 9, 2003 Perkowski
20030014400 January 16, 2003 Siegel
20030028451 February 6, 2003 Ananian
20030028605 February 6, 2003 Millett et al.
20030032409 February 13, 2003 Hutcheson et al.
20030035138 February 20, 2003 Schilling
20030036914 February 20, 2003 Fitzpatrick et al.
20030040970 February 27, 2003 Miller
20030041008 February 27, 2003 Grey et al.
20030046149 March 6, 2003 Wong
20030069740 April 10, 2003 Zeidman
20030069790 April 10, 2003 Kane
20030069825 April 10, 2003 Hoffman et al.
20030083961 May 1, 2003 Bezos et al.
20030088467 May 8, 2003 Culver
20030088511 May 8, 2003 Korboulonis et al.
20030093331 May 15, 2003 Childs et al.
20030097352 May 22, 2003 Gutta et al.
20030105682 June 5, 2003 Dicker et al.
20030110100 June 12, 2003 Wirth, Jr.
20030119492 June 26, 2003 Timmins et al.
20030131095 July 10, 2003 Kumhyr et al.
20030139969 July 24, 2003 Scroggie et al.
20030140007 July 24, 2003 Kramer et al.
20030140121 July 24, 2003 Adams
20030158792 August 21, 2003 Perkowski
20030163340 August 28, 2003 Fitzpatrick et al.
20030167213 September 4, 2003 Jammes et al.
20030167222 September 4, 2003 Mehrotra et al.
20030177103 September 18, 2003 Ivanov et al.
20030187745 October 2, 2003 Hobday et al.
20030200156 October 23, 2003 Roseman et al.
20030204449 October 30, 2003 Kotas et al.
20030217002 November 20, 2003 Enborg
20030220835 November 27, 2003 Barnes, Jr.
20040006509 January 8, 2004 Mannik et al.
20040015416 January 22, 2004 Foster et al.
20040029567 February 12, 2004 Timmins et al.
20040041836 March 4, 2004 Zaner et al.
20040044563 March 4, 2004 Stein
20040055017 March 18, 2004 Delpuch et al.
20040058710 March 25, 2004 Timmins et al.
20040073476 April 15, 2004 Donahue et al.
20040078388 April 22, 2004 Melman
20040107136 June 3, 2004 Nemirofsky et al.
20040117242 June 17, 2004 Conrad et al.
20040122083 June 24, 2004 Pettit et al.
20040122681 June 24, 2004 Ruvolo et al.
20040122735 June 24, 2004 Meshkin
20040122855 June 24, 2004 Ruvolo et al.
20040128183 July 1, 2004 Challey et al.
20040128283 July 1, 2004 Wang et al.
20040128320 July 1, 2004 Grove et al.
20040143731 July 22, 2004 Audebert et al.
20040148232 July 29, 2004 Fushimi et al.
20040172323 September 2, 2004 Stamm
20040172379 September 2, 2004 Mott et al.
20040174979 September 9, 2004 Hutton et al.
20040186766 September 23, 2004 Fellenstein et al.
20040199496 October 7, 2004 Liu et al.
20040199905 October 7, 2004 Fagin et al.
20040204989 October 14, 2004 Dicker et al.
20040204991 October 14, 2004 Monahan et al.
20040230989 November 18, 2004 Macey et al.
20040240642 December 2, 2004 Crandell et al.
20040249727 December 9, 2004 Cook, Jr. et al.
20040267717 December 30, 2004 Slackman
20050002166 January 6, 2005 Dinnage et al.
20050010925 January 13, 2005 Khawand et al.
20050038733 February 17, 2005 Foster et al.
20050044254 February 24, 2005 Smith
20050055306 March 10, 2005 Miller et al.
20050060664 March 17, 2005 Rogers
20050097204 May 5, 2005 Horowitz et al.
20050114229 May 26, 2005 Ackley et al.
20050120311 June 2, 2005 Thrall
20050131837 June 16, 2005 Sanctis et al.
20050144064 June 30, 2005 Calabria et al.
20050193333 September 1, 2005 Ebert
20050197846 September 8, 2005 Pezaris et al.
20050197950 September 8, 2005 Moya et al.
20050198031 September 8, 2005 Pezaris et al.
20050202390 September 15, 2005 Allen et al.
20050203888 September 15, 2005 Woosley et al.
20050216300 September 29, 2005 Appelman et al.
20050262067 November 24, 2005 Lee et al.
20050273378 December 8, 2005 MacDonald-Korth et al.
20060009994 January 12, 2006 Hogg et al.
20060010105 January 12, 2006 Sarakkai et al.
20060015498 January 19, 2006 Sarmiento et al.
20060031240 February 9, 2006 Eyal et al.
20060041638 February 23, 2006 Whittaker et al.
20060058048 March 16, 2006 Kapoor et al.
20060069623 March 30, 2006 MacDonald Korth et al.
20060085251 April 20, 2006 Greene
20060173817 August 3, 2006 Chowdhury et al.
20060206479 September 14, 2006 Mason
20060218049 September 28, 2006 Walker et al.
20060230035 October 12, 2006 Bailey et al.
20060235752 October 19, 2006 Kavanagh et al.
20060259360 November 16, 2006 Flinn et al.
20060271671 November 30, 2006 Hansen
20060282304 December 14, 2006 Bedard et al.
20070005424 January 4, 2007 Arauz
20070027760 February 1, 2007 Collins et al.
20070027814 February 1, 2007 Fouriniemi
20070073641 March 29, 2007 Perry et al.
20070077025 April 5, 2007 Mino
20070078726 April 5, 2007 MacDonald Korth et al.
20070078849 April 5, 2007 Slothouber
20070083437 April 12, 2007 Hamor
20070094597 April 26, 2007 Rostom
20070100803 May 3, 2007 Cava
20070130090 June 7, 2007 Staib et al.
20070160345 July 12, 2007 Sakai et al.
20070162379 July 12, 2007 Skinner
20070174108 July 26, 2007 Monster
20070192168 August 16, 2007 Van Luchene
20070192181 August 16, 2007 Asdourian
20070206606 September 6, 2007 Coleman et al.
20070214048 September 13, 2007 Chan et al.
20070226679 September 27, 2007 Jayamohan et al.
20070233565 October 4, 2007 Herzog et al.
20070239534 October 11, 2007 Liu et al.
20070245013 October 18, 2007 Saraswathy et al.
20070260520 November 8, 2007 Jha et al.
20070282666 December 6, 2007 Afeyan et al.
20070288298 December 13, 2007 Gutierrez et al.
20070299743 December 27, 2007 Staib et al.
20080015938 January 17, 2008 Haddad et al.
20080021763 January 24, 2008 Merchant
20080052152 February 28, 2008 Yufik
20080071640 March 20, 2008 Nguyen
20080082394 April 3, 2008 Floyd et al.
20080103893 May 1, 2008 Nagarajan et al.
20080120342 May 22, 2008 Reed et al.
20080126205 May 29, 2008 Evans et al.
20080126476 May 29, 2008 Nicholas et al.
20080133305 June 5, 2008 Yates et al.
20080140765 June 12, 2008 Kelaita et al.
20080162574 July 3, 2008 Gilbert
20080195476 August 14, 2008 Marchese et al.
20080201218 August 21, 2008 Broder et al.
20080215456 September 4, 2008 West et al.
20080288338 November 20, 2008 Wiseman et al.
20080294536 November 27, 2008 Taylor et al.
20080300909 December 4, 2008 Rikhtverchik et al.
20080301009 December 4, 2008 Plaster et al.
20080305869 December 11, 2008 Konforty et al.
20080313010 December 18, 2008 Jepson et al.
20090006190 January 1, 2009 Lucash et al.
20090030755 January 29, 2009 Altberg et al.
20090030775 January 29, 2009 Vieri
20090037355 February 5, 2009 Brave et al.
20090106080 April 23, 2009 Carrier et al.
20090106127 April 23, 2009 Purdy et al.
20090110181 April 30, 2009 Koenig et al.
20090119167 May 7, 2009 Kendall et al.
20090157537 June 18, 2009 Miller
20090164323 June 25, 2009 Byrne
20090164442 June 25, 2009 Shani et al.
20090182589 July 16, 2009 Kendall et al.
20090204848 August 13, 2009 Kube et al.
20090222348 September 3, 2009 Ransom et al.
20090222737 September 3, 2009 Liesche et al.
20090228918 September 10, 2009 Rolff et al.
20090234722 September 17, 2009 Evevsky
20090240582 September 24, 2009 Sheldon-Neal et al.
20090276284 November 5, 2009 Yost
20090276305 November 5, 2009 Clopp
20090292677 November 26, 2009 Kim
20090293019 November 26, 2009 Raffel et al.
20090313173 December 17, 2009 Singh et al.
20100042684 February 18, 2010 Broms et al.
20100070448 March 18, 2010 Omoigui
20100076816 March 25, 2010 Phillips
20100076851 March 25, 2010 Jewell, Jr.
20100094673 April 15, 2010 Lobo et al.
20100107123 April 29, 2010 Sareen et al.
20100145831 June 10, 2010 Esfandiari et al.
20100146413 June 10, 2010 Yu
20100228617 September 9, 2010 Ransom et al.
20110010656 January 13, 2011 Mokotov
20110055054 March 3, 2011 Glasson
20110060621 March 10, 2011 Weller et al.
20110103699 May 5, 2011 Ke et al.
20110131253 June 2, 2011 Peukert et al.
20110137973 June 9, 2011 Wei
20110145226 June 16, 2011 Gollapudi et al.
20110153383 June 23, 2011 Bhattacharjya et al.
20110153663 June 23, 2011 Koren et al.
20110173076 July 14, 2011 Eggleston et al.
20110191319 August 4, 2011 Nie et al.
20110196802 August 11, 2011 Ellis et al.
20110225050 September 15, 2011 Varghese
20110231226 September 22, 2011 Golden
20110231383 September 22, 2011 Smyth et al.
20110258049 October 20, 2011 Ramer et al.
20110271204 November 3, 2011 Jones et al.
20110276513 November 10, 2011 Erhart et al.
20110289068 November 24, 2011 Teevan et al.
20120005187 January 5, 2012 Chavanne
20120030067 February 2, 2012 Pothukuchi et al.
20120084135 April 5, 2012 Nissan et al.
20120158715 June 21, 2012 Maghoul et al.
20120164619 June 28, 2012 Meer
20120166299 June 28, 2012 Heinstein et al.
20120203723 August 9, 2012 Huang et al.
20120231424 September 13, 2012 Caiman et al.
20120233312 September 13, 2012 Ramakumar et al.
20120278388 November 1, 2012 Kleinbart et al.
20120284336 November 8, 2012 Schmidt et al.
20120323725 December 20, 2012 Johnston et al.
20130031470 January 31, 2013 Daly, Jr.
20130073392 March 21, 2013 Allen et al.
20130080200 March 28, 2013 Connolly et al.
20130080426 March 28, 2013 Chen et al.
20130085893 April 4, 2013 Bhardwaj et al.
20130144870 June 6, 2013 Gupta et al.
20130145254 June 6, 2013 Masuko et al.
20130151331 June 13, 2013 Avner et al.
20130151388 June 13, 2013 Falkenborg et al.
20130185164 July 18, 2013 Pottjegort
20130191409 July 25, 2013 Zeng et al.
20130254059 September 26, 2013 Teo
20130268561 October 10, 2013 Christie et al.
20140019313 January 16, 2014 Hu et al.
20140025509 January 23, 2014 Reisz et al.
20140032544 January 30, 2014 Mathieu et al.
20140114680 April 24, 2014 Mills et al.
20140136290 May 15, 2014 Schiestl et al.
20140172652 June 19, 2014 Pobbathi et al.
20140180758 June 26, 2014 Agarwal et al.
20140200959 July 17, 2014 Sarb et al.
20140259056 September 11, 2014 Grusd
20140289005 September 25, 2014 Laing et al.
20140337090 November 13, 2014 Tavares
20140372415 December 18, 2014 Fernandez-Ruis
20150019958 January 15, 2015 Ying et al.
20150089524 March 26, 2015 Cremonesi et al.
20150142543 May 21, 2015 Lellouche
20150286742 October 8, 2015 Zhang
20150287066 October 8, 2015 Wortley et al.
20170235788 August 17, 2017 Borisyuk
20170344622 November 30, 2017 Islam et al.
20200065357 February 27, 2020 Noursalehi et al.
Foreign Patent Documents
2253543 March 1997 CA
2347812 May 2000 CA
0636993 April 1999 EP
0807891 May 2000 EP
1241603 September 2002 EP
2397400 July 2004 GB
2424098 September 2006 GB
2001283083 December 2001 JP
2002318935 October 2002 JP
2007021920 February 2007 JP
2009505238 February 2009 JP
WO1997017663 May 1997 WO
WO1998032289 July 1998 WO
WO1998047082 October 1998 WO
WO1998049641 November 1998 WO
WO1999059283 November 1999 WO
WO2000025218 May 2000 WO
WO20000068851 November 2000 WO
WO2001009803 February 2001 WO
WO2001082135 November 2001 WO
WO2001097099 December 2001 WO
WO2002037234 May 2002 WO
WO2003094080 November 2003 WO
WO2007021920 February 2007 WO
WO2012093410 July 2012 WO
WO2015116038 August 2015 WO
WO2015176071 November 2015 WO
Other references
  • Teo, “Organizational Factors of Success in Using EDIS: A Survey of Tradenet Participants,” Electronic Markets—The International Journal, Oct. 1993, 2 pages, vol. 3, No. 3.
  • Tjostheim et al., “A case study of an on-line auction for the World Wide Web,” printed from www.nr.no/gem/elcom/puplikasjoner/enter98e.html on Jun. 10, 1990, 10 pages.
  • Turban, “Auctions and Bidding on the Internet: An Assessment,” Electronic Markets—The International Journal, Dec. 1997, 5 pages, vol. 7, No. 4.
  • ubid.com, “How do I Updated my Address, Phone, Credit Card, Password, etc.?” printed from web.archive.org/web/20010208113903/www.ubid.com/help/topic13asp on Aug. 30, 2007.
  • ubid.com, “How do I track my shipment?” printed from web.archive.org/web/20010331032659/www.ubid.com/help/topic27.asp on Aug. 30, 2007.
  • ubid.com, “Can I track all of my bids from My Page?” printed from web.archive.org/web/20010208114049/www.ubid.com/help/topic14.asp on Aug. 30, 2007.
  • Van Heck et al., “Experiences with Electronic Auctions in the Dutch Flower Industry,” Electronic Markets—The International Journal, Dec. 1997, 6 pages, vol. 7, No. 4.
  • Verizon Wireless, “Verizon Wireless Customers Get It NowSM; Get Games, Get Pix, Get Ring Tones and Get Going in Full Color,” press release to PRNEWSWIRE, Sep. 23, 2002.
  • Warbelow et al., “AUCNET: TV Auction Network System,” Harvard Business School 9-190-001, Jul. 19, 1989, Rev. Apr. 12, 1996, pp. 1-15.
  • Weber, “How Financial Markets are Going On-line,” Electronic Markets—The International Journal, Oct. 1993, 2 pages. vol. 3, No. 3.
  • Wireless Internet, “DailyShopper Selects 2Roam to Enable Mobile Customers to Retrieve Nearby Sales and Promotions Information,” Wireless Internet, Apr. 2001.
  • Wireless Week, “Verizon Wireless Gets Going on BREW Agenda,” Wireless Week, Sep. 23, 2002.
  • xchanger.net, webpage printed from www.auctiva.com/showcases/as_4sale.asp?uid=exchanger, undated but at least as early as Oct. 12, 2000.
  • Yu et al., “Distributed Reputation Management for Electronic Commerce,” Computational Intelligence, 2002, pp. 535-549, vol. 18, No. 4.
  • Zetmeir, Auction Incentive Marketing, print of all pages of website found at home.earthlink.net/˜bidpointz/ made Oct. 8, 2004.
  • Zimmermann, “Integration of Financial Services: The TeleCounter,” Electronic Markets—The International Journal, Oct. 1993, 1 page, vol. 3, No. 3.
  • Zwass, “Electronic Commerce: Structures and Issues,” International Journal of Electronic Commerce, Fall 1996, pp. 3-23, vol. 1, No. 1.
  • Message Passing from Wikipedia, archived May 6, 2016, retrieved from https://en.wikipedia.org/wiki/message_passing, 4 pages.
  • Di et al., “A New Implementation for Ontology Mapping Based enterprise Semantic Interoperation,” by Xiaofeng Di and Yushun Fan, Applied Mechanics and Materials, vols. 16-19 (2009), pp. 644-648 (Year:2009).
  • Nicolle et a., “XML Integration and Toolkit for B2B Applications,” by Christophe Nicolle, Kokou Yetongnon, and Jean-Claude Simon, Journal of Database Management, Oct.-Dec. 2003 (Year: 2003).
  • V. Aksakalli, Optimizing direct response in Internet display advertising, Elsevier, vol. 11, Issue 3, May-Jun. 2012, pp. 229-240. (Year: 2012).
  • Gallagher et al. A framework for targeting banner advertising on the internet. IEEE, pp. 265-274 (Year: 1997).
  • Alex, Neil,“Optimizing Search Results in Elasticsearch with Scoring and Boosting”, Mar. 18, 2015, Qbox.io, accessed at [https://qbox.io/blog/optimizing-search-results-in-elasticsearch0with-scoring-and-boosting] (year: 2015).
  • Hybrid algorithms for recommending new items. Cremonesi et al., ResearchGate, Google, (year:2011).
  • Lee, “AUCNET: Electronic Intermediary for Used-Car Transactions,” Electronic Market—The International Journal, Dec. 1997, pp. 24-28, vol. 7, No. 4.
  • T.Y. Lee, S. Li and R. Wei, “Needs-Centric Searching and Ranking Based on Customer Reviews,” 2008 10th IEEE Conference on E-Commerce Technology and the Fifth IEEE Conference on Enterprise Computing, E-Commerce and E-Services, Washington, DC, 2008, pp. 128-135. (Year: 2008).
  • Levy, Michael, and Dhruv Grewal. “Supply chain management in a networked economy.” Journal Retailing 76.4 (2000): 415-429.
  • LIVE365 press release, “Live365 to Offer Opt-ln Advertising on Its Website,” Oct. 15, 2004.
  • London Business School, “Overture and Google: Internet Pay-Per-Click (PPC) Advertising Options,” Mar. 2003.
  • M2 Presswire, “Palm, Inc.: Palm unveils new web browser optimised for handhelds; HTML browser offers high-speed web-browsing option,” Mar. 13, 2002.
  • Malone et al., “Electronic Markets and Electronic Hierarchies,” Communications of the ACM, Jun. 1987, pp. 484-497, vol. 30, No. 6.
  • Mansell et al., “Electronic Trading Networks: The Route to Competitive Advantage?” Electronic Markets—The International Journal, Oct. 1993, 1 page, vol. 3, No. 3.
  • Mardesich, “Onsale takes auction gavel electronic,” Computer Reseller News, Jul. 8, 1996, pp. 2, 32.
  • Marteau, “Shop with One Click, Anywhere, Anytime,” Information Management and Consulting, 2000, pp. 44-46, vol. 15, No. 4.
  • Massimb et al., “Electronic Trading, Market Structure and Liquidity,” Financial Analysts Journal, Jan.-Feb. 1994, pp. 39-49.
  • McGinnity, “Build Your Weapon,” PC Magazine, Apr. 24, 2011, printed from www.pcmag.com/print_article2?0,1217, a%253D3955,00.asp.
  • Meade, “Visual 360: a performance appraisal system that's ‘fun,’” HR Magazine, 44, 7, 118(3), Jul. 1999.
  • “Mediappraise: Mediappraise Receives National Award for Web-Based Technology That Enables Companies to Solve Thomy HR Problem,” Dec. 14, 1998.
  • Medvinsky et al., “Electronic Currency for the Internet,” Electronic Markets—The International Journal, Oct. 1993, 2 pages, vol. 3, No. 3.
  • metails.com, www.metails.com homepage, printed Oct. 13, 2004.
  • Microsoft Computer Dictionary, Fifth Edition, front matter and p. 33.
  • Microsoft Computer Dictionary, Fifth Edition, front matter, back matter, and pp. 479,486.
  • Neches, “FAST—A Research Project in Electronic Commerce,” Electronic Markets—The International Journal, Oct. 1993, 4 pages, vol. 3., No. 3.
  • Neisser, “Which is better for Social Media Monitoring: TweetDeck or SproutSocial” Mar. 17, 2011, Social Media Examiner, https://www.socialmediaexaminer.com/which-is-better-for-social-media-monitoring-tweetdeck-or-sproutsocial/.
  • Neo, “The implementation of an electronic market for pig trading in Singapore,” Journal of Strategic Information Systems, Dec. 1992, pp. 278-288, vol. 1, No. 5.
  • O'Mahony, “An X.500-based Product Catalogue,” Electronic Markets—The International Journal, Oct. 1993, 2 pages, vol. 3, No. 3.
  • “Onsale: Onsale Brings Thrill of Auctions and Bargain Hunting Online: Unique Internet retail services debuts with week-long charity auction for the Computer Museum in Boston,” May 24, 1995, printed from www.dialogweb.com/cgi/dwclient?dwcommand,DWEBPRINT%20810-489267.
  • “Onsale joins fray as online shopping pcks up speed: Internet Booms,” Comptuer Reseller News, Jun. 5, 1995.
  • Palm, Inc., PalmTM Web Pro Handbook, copyright 2002-2003.
  • Post et al., “Application of Auctions as a Pricing Mechanism for the Interchange of Electric Power,” IEEE Transactions of Power Systems, Aug. 1995, pp. 1580-1584, vol. 10, No. 3.
  • Preist et al., “Adaptive agents in a persistent shout double auction,” International Conference on Information and Computation, Proceedings of the first international conference on information and computation economies, Oct. 25-28, 1998, Charleston, United States, pp. 11-18.
  • Qualcomm, “Brew Developer Support,” printed from web.archive.org/web/20020209194207/http://www.qualcomm.com/brew/developer/support/kb/52.html on Aug. 30, 2007.
  • RCR Wireless News, “Lockheed Martin to use 2Roam's technology for wireless platform,” RCR Wireless News, Sep. 10, 2001.
  • Reck, “Formally Specifying an Automated Trade Execution System,” J. Systems Software, 1993, pp. 245-252, vol. 21.
  • Reck, “Trading-Process Characteristics of Electronic Auctions,” Electronic Markets—The International Journal, Dec. 1997, pp. 17-23, vol. 7, No. 4.
  • repcheck.com, www.repcheck.com homepage, printed from web.archive.org/web/20020330183132/http://repcheck.com on Sep. 5, 2009.
  • Resnick et al., “Reputation Systems,” Communications of the ACM, Dec. 2000, pp. 45-48, vol. 43, No. 12.
  • Rockoff et al., “Design of an Internet-based system for remote Dutch auctions,” Internet Research: Electronic Networking Applications and Policy, 1995, pp. 10-16, vol. 5, No. 4.
  • Rodriguez, Camille, HootSuite vs. social Oomph vs. Tweekdeck, Jan. 4, 2012, http://polkadotimpressions.com/2012/01/04/hootsuite-vs-social-oopmphvs.tweetdeck/ (Year: 2012).
  • Rose, “Vendors strive to undo Adobe lock-hold,” Computer Reseller News, Feb. 5, 1996, n 66669, p. 71(7).
  • Ross, David Frederick, Frederick S. Weston, and W. Stephen. Introduction to supply chain management technologies. CRC Press, 2010.
  • Rysavy, “Mobile-commerce ASPs do the legwork,” Network Computing, Jan. 22, 2001, p. 71, 6 pgs., vol. 12, No. 2.
  • Saunders, “AdFlight to Offer WAP Ads,” Oct. 17, 2000, printed from clickz.com/487531/print.
  • Schaffer, Neil, The Top 20 Twitter clients—HootSuite, TweetDeck and More, Jan. 31, 2012, https://maximizesocialbusinss.com/top-20-twitter-clients-2012-9175/ (Year: 2012).
  • Schmid, “Electronic Markets,” Electronic Markets—The International Journal, Oct. 1993, 2 pages, vol. 3, No. 3.
  • Schwankert, “Matsushita Taps 2Roam for Wireless Solutions,” www.internetnews.com/bus-news.article.php/674811, Feb. 2, 2001.
  • Sen, “Inventory and Pricing Models for Perishable Products,” Doctor of Philosophy Dissertation—University of Southern California, Aug. 2000.
  • Siegmann, “Nowhere to go but up,” PC Week, Oct. 23, 1995, 3 pages, vol. 12, No. 42.
  • Telephony Staff, “Air-ASP,” Telephony Online, Oct. 2, 2000, 3 pages.
  • 2Roam, Inc., multiple archived pages of www.2roam.com retrieved via Internet Archive Wayback Machine on Jun. 10, 2008.
  • Alt et al., “Bibliography on Electronic Commerce,” Electronic Markets—The International Journal, Oct. 1993, 5 pages, vol. 3, No. 3.
  • Alt et al., “Computer Integrated Logistics,” Electronic Markets—The International Journal, Oct. 1993, 1 page, vol. 1, No. 3.
  • Anonymous, Image manipulation (image-editing software and image-manipulation systems)(Seybold Special Report, Part II), Seybold Report on Publishing Systems, May 15, 1995, pS35(9), vol. 24, No. 18.
  • auctionwatch.com, multiple pages—including search results for “expedition,” printed Apr. 21, 2011.
  • auctiva.com, multiple pages, undated but website copyright date is “1999-2000.”
  • Ball et al., “Supply chain infrastructures: system integration and information sharing,” ACM SIGMOD Record, 2002, vol. 31, No. 1, pp. 61-66.
  • Berger et al., “Random Ultiple-Access Communication and Group Testing,” IEEE, 1984.
  • Braganza, “Is Resarch at Cranfield—A Look at the Future,” Electronic Markets—The International Journal, Oct. 1993, 1 page, vol. 3, No. 3.
  • Brecht et al., “The IM 2000 Research Programme,” Electronic Markets—The International Journal, Oct. 1993, 1 page, vol. 3, No. 3.
  • Business Wire business/technology editors, “Sellers Flock to OutletZoo.com as New Automatic Price Drop Method Moves Excess Inventory Online,” Business Wire, Oct. 25, 1999.
  • Business Wire business editors/high-tech writers, “PictureWorks Technology, Inc. Expands in Real Estate Market with Adoption of Rimfire on REALTOR.com,” Business Wire, Nov. 8, 1999.
  • Business Wire business editors/high-tech writers, “PictureWorks Technology, Inc. Shows Strong Revenue Growth in Internet Imaging Business,” Business Wire, Nov. 10, 1999.
  • Business Wire business editors/high-tech writers, “2Roam Partners with Pumatech to Delivery Wireless Alerts,” Business Wire, Dec. 18, 2000.
  • Business Wire business editors/high-tech writers, “2Roam Takes eHow's How-to Solutions Wireless: With 2Roam, the Web's One-Stop Source for getting Things Done is on More Wireless Devices, with Ability to Purchase Its Products from Anywhere,” Business Wire, Oct. 2, 2000.
  • Business Wire business editors/high-tech writers, “2Roam Drives Hertz to the Wireless Web: Number One Car Rental Company to Provide Customers Wireless Access from Any Device,” Business Wire, Aug. 7, 2001.
  • buy.com, www.buy.com homepage, printed Oct. 13, 2004.
  • Chen et al., “Detecting Web Page Structure for Adaptive Viewing on Small Form Factor Devices,” ACM, May 20-24, 2003.
  • Chen, M. (2007). Knowledge assisted data management and retrieval in multimedia database systems (Order No. 3268643).
  • Y.K. Choi and S. K. Kim, “An auxiliary reccomendation system for repetitively purchasing items in E-commerce,” 2014 International Conference on Big Data and Smart Computing (BIGCOMP), Bangkok, 2014, pp. 96-98. (Year 2014).
  • Clarke, “Research Programme in Supra-organizational Systems,” Electronic Markets—The International Journal, Oct. 1993, 2 pages, vol. 3, No. 3.
  • Clemons et al., “Evaluating the prospects for alternative electronic securities markets,” Proceedings of the twelfth international conference on information systems, New York, New York, United States, pp. 53-64, 1991.
  • Fan, J., Keim, F.A., Gao, Y., Luo, H. and Li, Z. (2009). JustClick: Personalized Image Recommendation via Exploratory Search from Large-Scale Flickr Images. Feb. 2009. IEEE Transactions on Circuits and Systems for Video Technology, 19(2), pp. 2730288. (Year: 2009).
  • friendster.com, homepage and “more info” pages, printed Apr. 29, 2004.
  • Google News archive search for “2Roam marketing” performed over the date range 2000-2003.
  • Google News archive search for “2Roam SMS” performed over the date range 2000-2008.
  • Grabowski et al., “Mobile-enabled grid middleware and/or grid gateways,” GridLab—A Grid Application Toolkit and Testbed, Work Package 12—Access for Mobile Users, Jun. 3, 2003.
  • Graham, “The Emergence of Linked Fish Markets in Europe,” Electronic Markets—The International Journal, Jul. 1993, 4 pages, vol. 8, No. 2.
  • Gunthorpe et al., “Portfolio Composition and the Investment Horizon,” Financial Analysts Journal, Jan.-Feb. 1994, pp. 51-56.
  • Halperin, “Toward a Process Handbook for Organizational Coordination Processes,” Electronic Markets—The International Journal, Oct. 1993, 1 page, vol. 3, No. 3.
  • Hess et al., “Computerized Loan Origination Systems: An Industry Case Study of the Electronic Markets Hypothesis,” MIS Quarterly, Sep. 1994, pp. 251-275.
  • IBM, “Anyonymous Delivery of Goods in Electronic Commerce,” IBM Technical Disclosure Bulletin, Mar. 1996, pp. 363-366, vol. 39, No. 3.
  • IBM, “Personal Optimized Decision/Transaction Program,” IBM Technical Disclosure Bulletin, Jan. 1995, pp. 83-84, vol. 38, No. 1.
  • Icrossing, “Icrossing Search Synergy: Natural & Paid Search Symbiosis,” Mar. 2007.
  • IEEE 100—The Authoritative Dictionary of IEEE Standard Terms, Seventh Edition, 2000. Entire book cited; table of contents, source list, and terms beginning with A included. ISBN 0-7381-2601-2a.
  • Ives et al., “Editor's Comments—MISQ Central: Creating a New Intellectual Infrastructure,” MIS Quarterly, Sep. 1994, p. xxxv.
  • Joshi, “Information visibility and its effect on supply chain dynamics,” Ph.D. dissertation, Massachusetts Institute of Technology, 2000 (fig. 4.5; p. 45).
  • Klein, “Information Logistics,” Electronic Markets—The International Journal, Oct. 1993, pp. 11-12, vol. 3, No. 3.
  • Klein, “Introduction to Electronic Auctions,” Electronic Markets—The International Journal, Dec. 1997, 4 pages, vol. 7, No. 4.
  • Kubicek, “The Organization Gap,” Electronic Markets—The International Journal, Oct. 1993, 1 page, vol. 3, No. 3.
  • S. Kulkarni, A. M. Sankpal, R.R. Mudholkar and Kirankumari, “Recommendation engine: Matching individual/group profiles for better shopping experience,” 2013 15th International Conference on Advanced Computing Technologies (ICACT), Rajampet, 2013, pp. 1-6. (Year: 2013).
  • Kuula, “Telematic Services in Finland,” Electronic Markets—The International Journal, Oct. 1993, 1 page, vol. 3, No. 3.
  • Lalonde, “The EDI World Institute: An International Approach,” Electronic Markets—The International Journal, Oct. 1993, 1 page, vol. 3, No. 3.
  • Lee et al., “Intelligent Electronic Trading for Commodity Exchanges,” Electronic Markets—The International Journal, Oct. 1993, 2 pages, vol. 3, No. 3.
  • Lee et al., “Electronic Brokerage and Electronic Auction: The Impact of IT on Market Structures,” Proceedings of the 29th Annual Hawaii International Conference on System Sciences, 1996, pp. 397-406.
Patent History
Patent number: 11526653
Type: Grant
Filed: Apr 6, 2021
Date of Patent: Dec 13, 2022
Assignee: Overstock.com, Inc. (Midvale, UT)
Inventors: Sam Noursalehi (Salt Lake City, UT), Yugang Hu (Salt Lake City, UT), Allen Joel Dickson (Eldersburg, MD)
Primary Examiner: Scott T Baderman
Assistant Examiner: Barbara M Level
Application Number: 17/223,246
Classifications
Current U.S. Class: Computer Network Monitoring (709/224)
International Classification: G06F 40/00 (20200101); G06F 40/106 (20200101); G06N 20/00 (20190101); G06F 16/93 (20190101); G06N 7/00 (20060101);